A react-based starter app for using the Multimodal Live API over websockets with Gemini

Model Context Protocol Servers

Python tool for converting files and office documents to Markdown.

Get up and running with Llama 3, Mistral, Gemma, and other large language models.by adding more amd gpu support.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

A work-in-progress for Zcash Bitcoin Cross-Chain Atomic Transactions

A curated list of Model Context Protocol (MCP) servers

Verified Rust for low-level systems code

An implementation of a post quantum anonymous credential scheme

Official repository for LTX-Video

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

A verification toolchain for Rust programs

An experiment in scalable routing as an encrypted IPv6 overlay network

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

PADL - Private, Auditable and Distributed ledger, is a tool based on zero-knowledge proofs for exploring and building private and auditable ledger in blockchain applications of financial institutes.

Get your documents ready for gen AI

TLS 1.3 Specification

Free to host calendar availability picker - open-source cal.com / calendly alternative built on Google-Apps-Script for Gmail users. Built with modern technologies like React, TypeScript, Shadcn/UI,…

A React-based web app project that enables running Claude AI’s Artifacts either locally or on your own server.

The ultimate TypeScript environment for Circom development

Minimal LLM inference in Rust

Entropy Based Sampling and Parallel CoT Decoding

Prompt, run, edit, and deploy full-stack web applications

Build real-time multimodal AI applications 🤖🎙️📹

Implementation of a forward-only double-entry accounting method with a relational database.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/